The following pages link to (Q4934335):
Displaying 14 items.
- Weighted last-step min-max algorithm with improved sub-logarithmic regret (Q465257) (← links)
- Kernelization of matrix updates, when and how? (Q465262) (← links)
- A generalized online mirror descent with applications to classification and regression (Q493737) (← links)
- Exponentiated gradient versus gradient descent for linear predictors (Q675044) (← links)
- Relative expected instantaneous loss bounds (Q1604219) (← links)
- Piecewise linear lower and upper bounds for the standard normal first order loss function (Q1644563) (← links)
- Smooth calibration, leaky forecasts, finite recall, and Nash dynamics (Q1753290) (← links)
- Analysis of two gradient-based algorithms for on-line regression (Q1970199) (← links)
- An Upper Bound for Aggregating Algorithm for Regression with Changing Dependencies (Q2830280) (← links)
- (Q3014818) (← links)
- (Q3145619) (← links)
- Algorithmic Learning Theory (Q5464505) (← links)
- Worst-case bounds for the logarithmic loss of predictors (Q5945696) (← links)
- “Calibeating”: Beating forecasters at their own game (Q6180412) (← links)
